finding
active
finding:clt-on-gpt-2-small-with-expansion-factor-64-gives-49-152-features-per-layer-and-589-824-total-across-12-layersCLT on GPT-2 Small with expansion factor 64 gives 49,152 features per layer and 589,824 total across 12 layers
Training configuration.
Source paper
extracted_fromNeighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Main conclusion.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Best CLT on GPT-2 Small achieves L0 of 79 and 59% token accuracy, consistent with Ameisen et al.finding0.820Training quality of the CLT.
- GPT-4o-mini most consistent in reproducing persona-aligned atomic distributions across repeated generations
- C.7.1.
- Emergent scaling trend showing VS better exploits capabilities of larger models
- Demonstrates VS's capability to enable large models to perform on par with dedicated fine-tuned models for simulation
- Validates Assumption D.3 that instruction-tuned models prefer representative distributions, supporting the VS theoretical framework
- GPT-4.1 robustness collapse values
- GPT-4o insecure S=1.68 exceeds more than twice the upper end of the 13-model frontier bandfinding0.727Most extreme susceptibility spike, placing GPT-4o insecure well outside normal model distribution